HanyangLiu / HiPAL

Code for KDD'22 Applied Data Science Track submission -- HiPAL: A Deep Framework for Physician Burnout Prediction Using Activity Logs in Electronic Health Records

HiPAL

Code for KDD'22 Paper -- HiPAL: A Deep Framework for Physician Burnout Prediction Using Activity Logs in Electronic Health Records

Setup

pip install requirements.txt

To Run

Parse activities from EHR log files:

python log_parsing.py

Run HiPAL and its variants:

bash bash/run_hitcn_cv.sh

Run single-level models (FCN, CausalNet, ResTCN):

bash bash/run_single_level.sh

Run hierarchial RNNs (H-RNN, HiGRU):

bash bash/run_higru_cv.sh

Interpretable Burnout Prediction

Citation

Please consider citing our work if you find this repository useful!

@article{liu2022hipal,
  title={HiPAL: A Deep Framework for Physician Burnout Prediction Using Activity Logs in Electronic Health Records},
  author={Liu, Hanyang and Lou, Sunny S and Warner, Benjamin C and Harford, Derek R and Kannampallil, Thomas and Lu, Chenyang},
  journal={ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
  year={2022}
}